# Reassessing Layer Pruning in LLMs: New Insights and Methods

arXiv: https://arxiv.org/abs/2411.15558 · HTML: https://mlsanity.com/paper/2411.15558/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 75 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Builds on (most cited first, 30 of 60)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)

## Built on by (most cited first, 24 of 24)

- [SepPrune: Structured Pruning for Efficient Deep Speech Separation](https://mlsanity.com/paper/2505.12079/) (2025)
- [Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL](https://mlsanity.com/paper/2602.13035/) (2026)
- [Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs](https://mlsanity.com/paper/2509.10377/) (2025)
- [Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.19386/) (2026)
- [TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://mlsanity.com/paper/2508.01473/) (2025)
- [DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2509.13723/) (2025)
- [When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs](https://mlsanity.com/paper/2510.22228/) (2025)
- [FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition](https://mlsanity.com/paper/2505.21571/) (2025)
- [Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity](https://mlsanity.com/paper/2605.14075/) (2026)
- [Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization](https://mlsanity.com/paper/2607.08057/) (2026)
- [On the Limits of Layer Pruning for Generative Reasoning in Large Language Models](https://mlsanity.com/paper/2602.01997/) (2026)
- [The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models](https://mlsanity.com/paper/2510.23652/) (2025)
- [MedTri: A Platform for Structured Medical Report Normalization to Enhance Vision-Language Pretraining](https://mlsanity.com/paper/2602.22143/) (2026)
- [Latent Flow Transformer](https://mlsanity.com/paper/2505.14513/) (2025)
- [Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports](https://mlsanity.com/paper/2508.15845/) (2025)
- [ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices](https://mlsanity.com/paper/2506.09066/) (2025)
- [Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers](https://mlsanity.com/paper/2509.01161/) (2025)
- [A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture](https://mlsanity.com/paper/2509.01164/) (2025)
- [COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens](https://mlsanity.com/paper/2509.06836/) (2025)
- [Leveraging KV Similarity for Online Structured Pruning in LLMs](https://mlsanity.com/paper/2512.07090/) (2025)
- [HSCP: A Two-Stage Spectral Clustering Framework for Resource-Constrained UAV Identification](https://mlsanity.com/paper/2512.08983/) (2025)
- [SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs](https://mlsanity.com/paper/2608.25068/) (2026)
- [Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference](https://mlsanity.com/paper/2609.05275/) (2026)
- [Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models](https://mlsanity.com/paper/2610.05982/) (2026)

## Abstract (arXiv)

Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained environments. Layer pruning, as a simple yet effective compression method, removes layers of a model directly, reducing computational overhead. However, what are the best practices for layer pruning in LLMs? Are sophisticated layer selection metrics truly effective? Does the LoRA (Low-Rank Approximation) family, widely regarded as a leading method for pruned model fine-tuning, truly meet expectations when applied to post-pruning fine-tuning? To answer these questions, we dedicate thousands of GPU hours to benchmarking layer pruning in LLMs and gaining insights across multiple dimensions. Our results demonstrate that a simple approach, i.e., pruning the final 25% of layers followed by fine-tuning the textttlmhead and the remaining last three layer, yields remarkably strong performance. Following this guide, we prune Llama-3.1-8B-It and obtain a model that outperforms many popular LLMs of similar size, such as ChatGLM2-6B, Vicuna-7B-v1.5, Qwen1.5-7B and Baichuan2-7B. We release the optimal model weights on Huggingface, and the code is available on GitHub.